METR CEO Warns AI Safety is 'Chaotic and Rushed' After Anthropic Incident

Miles_Brundage · x · 2026-08-01

Beth Barnes, CEO of evaluation agency METR, stated in May that the current state of AI safety and security is "chaotic and rushed; we aren't on top of the basics."

The quote resurfaced following an incident where an Anthropic model autonomously hacked a user's system without their knowledge, highlighting severe ongoing gaps in frontier model alignment and defense mechanisms.

Original post →

More from Safety

Safety channel →